Review what Superset agents did while you were away by checking workspaces, tasks, and recent terminal output. Receive a concise digest of completed work, review requests, ongoing activity, and blockers, with the next actions listed first.
Digest of what the user's Paradev (formerly Superset) agents did while they were away, sweeping workspaces, tasks, and agent terminals to report what finished, what needs review, and what's blocked. Use when the user asks "what did my agents do", "what happened while I was away", wants a standup or summary of agent work, or returns after a break.
Run score Not tested
See how to installThis skill checks Superset workspaces, tasks, and agent terminal output to summarize what happened while you were away. It classifies each item as needing your review or input, in progress, blocked by an external issue, or idle with no remaining work. Items that need your attention come first, with the workspace, agent, status, and next action.
Use it after a break or when you want to review work agents did overnight. It saves you from checking each terminal one by one and helps surface review requests, questions, and errors. It also identifies workspaces with no remaining work that may be candidates for cleanup.
The skill uses the Superset CLI. Its sweep script requires bash and jq; if they are unavailable, it checks each workspace and terminal through the CLI. The usual summary is read-only: it does not send terminal input, change tasks, or clean up workspaces. It can publish an HTML report page when asked, but does not publish one without an explicit request.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 29, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
paradev is an alias for the superset CLI: every superset command here also runs as paradev.
Answer "what happened while I was away?" from real state, not guesses. Entirely read-only.
Run bash scripts/sweep.sh from this skill's directory (bash ${CLAUDE_SKILL_DIR}/scripts/sweep.sh in Claude Code). It lists workspaces and tasks, then for each workspace lists its terminals and reads the last screen of every agent terminal, tolerating individual failures. Pass --host <id> to sweep a remote host, --max-lines <n> to change the per-terminal tail (default 60).
If the script can't run (no bash, no jq), do the same by hand: superset workspaces list --local --json, superset tasks list --json, then per workspace superset terminals list --workspace <id> --json and superset terminals read --workspace <id> --terminal <terminalId> --max-lines 60.
The last screen of a terminal shows whether the agent finished, asked a question, or errored.
Lead with what needs the user, one line per item: workspace, agent, state, and the next action. Then in-flight, then completed, then stale-workspace cleanup suggestions. Keep the whole digest scannable: no terminal dumps, quote at most the single relevant line an agent printed.
Offer the digest as a page when someone other than the user will read it, or when they want it
to persist past the scrollback. Write the report you just composed to an .html file inside a
workspace, then publish that file: the CLI publishes a document, not your terminal output.
superset pages publish standup.html --workspace <id> --title "Standup" --label "what shipped overnight"
Publishing the same file from the same workspace each morning versions one page instead of
scattering a new one daily, so the history becomes the record of the week. A digest often runs
from outside any workspace, and a publish with no workspace is refused, so pass --workspace
explicitly. Offer it; never publish one unasked.
Never send input to a terminal, modify tasks, or clean anything up as part of the digest. Offer those as follow-ups and act only when asked.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Review how you use Superset and identify unused features that fit your workflow. Get a short list of suggestions, learn about each option, and set up selected features such as scheduled agents, parallel workspaces, or shared tasks.
Set up recurring tasks in Superset with an agent prompt, a schedule or event trigger, and a chosen execution workspace. After explicit confirmation, create the automation, check its saved settings, and review a real first run.
Browse pages, click controls, fill fields, and inspect screenshots or console messages through Superset's browser pane. Use it to preview a running web app, check interface behavior, and work through browser tasks in a visible session.
Build Stripe payments, subscriptions, and invoicing using verified documentation and API parameter definitions. The skill guides product selection, sandbox testing, and webhook handling, where server notifications determine payment and subscription state.
Verify a UI change or reproduce a bug in the running desktop app using the Chrome DevTools Protocol (CDP), a browser debugging interface. Follow the real user journey and compare screenshots with measurements such as route, scroll position, and persisted state.
Diagnose failed GitHub Actions runs by finding the first meaningful error, separating code problems from infrastructure issues and intermittent failures, and comparing the base branch. Get a focused report explaining the PR’s involvement and recommended next steps.